结合特征选择和大尺度谱聚类的极化SAR图像非监督分类

非监督分类是极化SAR图像解译的重要手段,但其分类结果易受到高维特征的影响。针对此问题,本文提出一种结合特征选择和大尺度谱聚类的极化SAR图像非监督分类方法。该方法首先深入分析并提取了极化SAR图像分类中常用的特征参数,包括基于测量数据及其简单线性变换的特征和极化目标分解的特征。然后通过聚类森林特征选择算法进行特征降维处理,去除冗余信息。最后利用过分割产生代表点并构建原始数据与代表点间的二分图,通过大尺度谱聚类算法完成图像的非监督分类。实验结果表明,该方法能够选取有效的特征组合,并得到较为满意的分类效果。      

Efficiently searching the important input variables using Bayesian discriminant

This paper focuses on enhancing feature selection (FS) performance on a classification data set. First, a novel FS criterion using the concept of Bayesian discriminant is introduced. The proposed criterion is able to measure the classification ability of a feature set (or, a combination of the weighted features) in a direct way. This guarantees excellent FS results. Second, FS is conducted by optimizing the newly derived criterion in a continuous space instead of by heuristically searching features in a discrete feature space. Using this optimizing strategy, FS efficiency can be significantly improved. In this study, the proposed supervised FS scheme is compared with other related methods on different classification problems in which the number of features ranges from 33 to over 12,000. The presented results are very promising and corroborate the contributions of this study.     

基于聚类识别的极化SAR图像分类

This paper presents a novel unsupervised image classification method for Polarimetric Synthetic Aperture Radar (PolSAR) data. The proposed method is based on a discriminative clustering framework that explicitly relies on a discriminative supervised classification technique to perform unsupervised clustering. To implement this idea, an energy function is designed for unsupervised PolSAR image classification by combining a supervised Softmax Regression (SR) model with a Markov Random Field (MRF) smoothness constraint. In this model, both the pixelwise class labels and classifiers are taken as unknown variables to be optimized. Starting from the initialized class labels generated by Cloude-Pottier decomposition and K-Wishart distribution hypothesis, the classifiers and class labels are iteratively optimized by alternately minimizing the energy function with respect to them. Finally, the optimized class labels are taken as the classification result, and the classifiers for different classes are also derived as a side effect. This approach is applied to real PolSAR benchmark data. Extensive experiments justify that the proposed approach can effectively classify the PolSAR image in an unsupervised way and produce higher accuracies than the compared state-of-the-art methods.     

基于无监督特征选择的高光谱图像分类方法

在高光谱图像分类中,丰富的数据提升了其地物 识别能力。然而,由于样本特 征数大且有标记训练样本点少,导致“维度灾难”问题。本文提出一种基于无监督特征选择 的高光谱图像分类方 法,该方法同时考虑数据的流形嵌入映射和稀疏表达,将特征选择问题转化为一个优 化问题,数据的流形嵌入和稀疏表达作为约束项加入目标函数。设计了三个目标函 数,第一个目标函数描述流形学习的局部性原则,第二个目标函数将原始样本点回归 到低维嵌入空间,第三个目标函数对回归系数进行正则化。针对目标函数非凸的问 题,用迭代的方法来解这个约束优化问题,给出了解该优化问题的算法。优选特征用 于参与后续的分类识别任务。在真实的高光谱数据集上的实验表明,新方法能够提高 分类的精度。     

Feature Selection for Genomic Signal Processing: Unsupervised,Supervised, and Self-Supervised Scenarios

An effective data mining system lies in the representation of pattern vectors. For many bioinformatic applications, data are represented as vectors of extremely high dimension. This motivates the research on feature selection. In the literature, there are plenty of reports on feature selection methods. In terms of training data types, they are divided into the unsupervised and supervised categories. In terms of selection methods, they fall into filter and wrapper categories. This paper will provide a brief overview on the state-of-the-arts feature selection methods on all these categories. Sample applications of these methods for genomic signal processing will be highlighted. This paper also describes a notion of self-supervision. A special method called vector index adaptive SVM (VIA-SVM) is described for selecting features under the self-supervision scenario. Furthermore, the paper makes use of a more powerful symmetric doubly supervised formulation, for which VIA-SVM is particularly useful. Based on several subcellular localization experiments, and microarray time course experiments, the VIA-SVM algorithm when combined with some filter-type metrics appears to deliver a substantial dimension reduction (one-order of magnitude) with only little degradation on accuracy.     

Genetic Sequence Classification and its Application to Cross-Species Homology Detection

Although large-scale classification studies of genetic sequence data are in progress around the world, very few studies compare different classification approaches, e.g. unsupervised and supervised, in terms of objective criteria such as classification accuracy and computational complexity. In this paper, we study such criteria for both unsupervised and supervised classification of a relatively large sequence data set. The unsupervised approach involves use of different sequence alignment algorithms (e.g., Smith-Waterman, FASTA and BLAST) followed by clustering using the Maximin algorithm. The supervised approach uses a suitable numeric encoding (relative frequencies of tuples of nucleotides followed by principal component analysis) which is fed to a Multi-layer Backpropagation Neural Network. Classification experiments conducted on IBM-SP parallel computers show that FASTA with unsupervised Maximin leads to best trade-off between accuracy and speed among all methods, followed by supervised neural networks as the second best approach. Finally, the different classifiers are applied to the problem of cross-species homology detection.     

基于半监督联合神经网络的调制识别算法

针对基于有监督学习通信信号分类算法需要大量有标签训练样本,而在实际场合大多无法满足数量要求的问题,提出利用数据驱动模型的半监督学习方法,通过对比预测编码无监督算法预训练和有监督学习相结合,利用LSTM (long short term memory)和ResNet (residual network)联合神经网络实现小样本自动提取特征,提高小样本条件下信号识别准确率。在真实通信调制信号集上实验表明,半监督联合神经网络结构较以往方法,识别准确率提升3%-20%,小样本条件下性能提高60%,同时在低信噪比条件下识别能力突出,0dB时对11种调制信号平均识别正确率达到92%,具有明显优势。      

基于子空间学习和伪标签回归的无监督特征选择

信息技术的快速发展产生了大量无标签高维数据。为了能够更好地处理这些数据,提出了一种基于子空间学习和伪标签回归的无监督特征选择方法。首先,从矩阵分解的角度将子空间学习和特征选择结合在一个框架中,2,1〗范数保证稀疏,在寻找原始数据空间低维表示的同时进行特征选择;其次,利用回归函数来学习特征子空间和伪标签之间的映射关系,利用伪标签和回归函数来指导无监督特征选择,以使选择出来的特征更具判别力;最后,通过引入图拉普拉斯来挖掘隐藏在样本空间和特征空间的局部结构信息。在六个公开的数据集上进行了实验,实验结果表明该方法要优于其他几种先进的无监督特征选择算法。      

特征选择与深度学习相结合的极化SAR图像分类

给出了一种特征选择与深度学习相结合的极化合成孔径雷达(polarimetric synthetic aperture radar, PolSAR)图像有监督分类算法。该算法首先根据极化SAR图像数据以及目标分解获取原始特征参数集,然后利用随机森林(Random Forest, RF)方法对特征参数集进行重要性评估,并根据特征重要性排名选择最优极化特征。以最优极,化特征为输入,通过卷积神经网络(convolutional neural network, CNN)学习多层特征信息,再利用训练好的网络模型对极化SAR图像进行分类。利用美国AIRSAR机载系统采集的实测数据进行实验,并同已有经典有监督分类算法进行比较,结果表明本文算法能够选取有效的极化特征,最终得到较为准确的分类效果。      

一种模型选择优化准则及其在高光谱图像非监督分类中的应用

选择合适的类别数是非监督分类中的一个关键问题.针对采用高斯混合建模的高光谱图像非监督分类问题,该文提出了一种基于主成分分析(PCA)的最小描述长度(MDL)型模型选择准则(文中简称为PMDL)来确定分类类别数,即根据PCA变换后保留的各主成分表达的数据方差不同而应具有不同的编码长度这一事实,在计算描述长度时对各维进行加权.分类过程中,论文采用期望最大化(Expectation Maximization)算法在合并的策略下对PCA变换后的数据求解混合模型,并应用所提出的准则进行模型选择从而确定待分类的类别数.仿真数据实验证实了新准则的有效性和优良的性能,并采用真实数据对该准则和整个算法进行了验证.     

基于部分标记数据进行人脸图像特征提取

针对无监督特征提取的识别率低与监督特征提取需要大量标记的问题,提出一种基于部分标记数据的半监督判别分析(SSDPA)特征提取法。本文方法能实现图像数据降维,避免线性判别分析(LDA)存在的小样本问题,达到提高识别率的目的。算法对图像进行离散余弦变换(DCT)变换;根据DCT图像的频率分布,利用部分标记数据计算SSDP;优先搜索SSDP高的DCT图像信息。将本文方法与其它方法进行组合,在不同人脸数据库上进行了实验。实验证明了本文方法的有效性,用较低的代价获得了优于传统方法的识别率。     

基于特征解耦的无监督水下图像增强

水介质的吸收和散射特性致使水下图像存在不同类型的失真,严重影响后续处理的准确性和有效性。目前有监督学习的水下图像增强方法依靠合成的水下配对图像集进行训练,然而由于合成的数据可能无法准确地模拟水下成像的基本物理机制,所以监督学习的方法很难应用于实际的应用场景。该文提出一种基于特征解耦的无监督水下图像增强方法,一方面,考虑获取同一场景下的清晰-非清晰配对数据集难度大且成本高,提出采用循环生成对抗网络将水下图像增强问题转换成风格迁移问题,实现无监督学习;另一方面,结合特征解耦方法分别提取图像的风格特征和结构特征,保证增强前后图像的结构一致性。实验结果表明,该方法可以在非配对数据训练的情况下,能够有效恢复水下图像的颜色和纹理细节。     

Semi-supervised feature selection with exploiting shared information among multiple tasks

Given several related tasks, multi-task feature selection determines the importance of features by mining the correlations between them. There have already many efforts been made on the supervised multi-task feature selection. However, in real-world applications, it’s noticeably time-consuming and unpractical to collect sufficient labeled training data for each task. In this paper, we propose a novel feature selection algorithm, which integrates the semi-supervised learning and multi-task learning into a joint framework. Both the labeled and unlabeled samples are sufficiently utilized for each task, and the shared information between different tasks is simultaneously explored to facilitate decision making. Since the proposed objective function is non-smooth and difficult to be solved, we also design an efficient iterative algorithm to optimize it. Experimental results on different applications demonstrate the effectiveness of our algorithm.     

Application of neural networks for sea ice classification inpolarimetric SAR images

Several automatic methods have been developed to classify sea ice types from fully polarimetric synthetic aperture radar (SAR) images, and these techniques are generally grouped into supervised and unsupervised approaches. In previous work, supervised methods have been shown to yield higher accuracy than unsupervised techniques, but suffer from the need for human interaction to determine classes and training regions. In contrast, unsupervised methods determine classes automatically, but generally show limited ability to accurately divide terrain into natural classes. In this paper, a new classification technique is applied to determine sea ice types in polarimetric and multifrequency SAR images, utilizing an unsupervised neural network to provide automatic classification, and employing an iterative algorithm to improve the performance. The learning vector quantization (LVQ) is first applied to the unsupervised classification of SAR images, and the results are compared with those of a conventional technique, the migrating means method. Results show that LVQ outperforms the migrating means method, but performance is still poor. An iterative algorithm is then applied where the SAR image is reclassified using the maximum likelihood (ML) classifier. It is shown that this algorithm converges, and significantly improves classification accuracy. The new algorithm successfully identifies first-year and multiyear sea ice regions in the images at three frequencies. The results show that L- and P-band images have similar characteristics, while the C-band image is substantially different. Classification based on single features is also carried out using LVQ and the iterative ML method. It is found that the fully polarimetric classification provides a higher accuracy than those based on a single feature. The significance of multilook classification is demonstrated by comparing the results obtained using four-look and single-look classifications     

Unsupervised learning of parsimonious mixtures on large spaces with integrated feature and component selection

Estimating the number of components (the order) in a mixture model is often addressed using criteria such as the Bayesian information criterion (BIC) and minimum message length. However, when the feature space is very large, use of these criteria may grossly underestimate the order. Here, it is suggested that this failure is not mainly attributable to the criterion (e.g., BIC), but rather to the lack of "structure" in standard mixtures-these models trade off data fitness and model complexity only by varying the order. The authors of the present paper propose mixtures with a richer set of tradeoffs. The proposed model allows each component its own informative feature subset, with all other features explained by a common model (shared by all components). Parameter sharing greatly reduces complexity at a given order. Since the space of these parsimonious modeling solutions is vast, this space is searched in an efficient manner, integrating the component and feature selection within the generalized expectation-maximization (GEM) learning for the mixture parameters. The quality of the proposed (unsupervised) solutions is evaluated using both classification error and test set data likelihood. On text data, the proposed multinomial version-learned without labeled examples, without knowing the "true" number of topics, and without feature preprocessing-compares quite favorably with both alternative unsupervised methods and with a supervised naive Bayes classifier. A Gaussian version compares favorably with a recent method introducing "feature saliency" in mixtures.     

Feature Selection Method by Applying Parallel Collaborative Evolutionary Genetic Algorithm

Feature selection is one of the important topics in text classification. However, most of existing feature selection methods are serial and inefficient to be applied to massive text data sets. In this ease, a feature selection method based on parallel collaborative evolutionary genetic algorithm is presented. The presented method uses genetic algorithm to select feature subsets and takes advantage of parallel collaborative evolution to enhance time efficiency, so it can quickly acquire the feature subsets which are more representative. The experimental results show that, for accuracy ratio and recall ratio, the presented method is better than information gain, x2 statistics, and mutual information methods; the consumed time of the presented method with only one CPU is inferior to that of these three methods, but the presented method is superior after using the parallel strategy.     

图强化典型相关分析及在图像识别中的应用

典型相关分析(CCA)作为一种传统特征提取算法已经成功应用于模式识别领域,其旨在找到使两组模态数据间相关性最大的投影方向,但其本身为一种无监督的线性方法,无法利用数据内在的几何结构和监督信息,难以处理高维非线性数据。为此该文提出一种新的非线性特征提取算法,即图强化典型相关分析(GECCA)。该算法利用数据中的不同成分构建多个成分图,有效保留了数据间的复杂流形结构,采用概率评估的方法使用类标签信息,并通过图强化的方式将几何流形和监督信息融合嵌入到典型相关分析框架。为了对该算法进行评估,分别在人脸和手写体数字数据集上设计了针对性实验,良好的实验结果显示出该算法在图像识别中的优势。     

Automatic tumor segmentation using knowledge-based techniques

A system that automatically segments and labels glioblastoma-multiforme tumors in magnetic resonance images (MRIs) of the human brain is presented. The MRIs consist of T1-weighted, proton density, and T2-weighted feature images and are processed by a system which integrates knowledge-based (KB) techniques with multispectral analysis. Initial segmentation is performed by an unsupervised clustering algorithm. The segmented image, along with cluster centers for each class are provided to a rule-based expert system which extracts the intracranial region. Multispectral histogram analysis separates suspected tumor from the rest of the intracranial region, with region analysis used in performing the final tumor labeling. This system has been trained on three volume data sets and tested on thirteen unseen volume data sets acquired from a single MRI system. The KB tumor segmentation was compared with supervised, radiologist-labeled “ground truth” tumor volumes and supervised K-nearest neighbors tumor segmentations. The results of this system generally correspond well to ground truth, both on a per slice basis and more importantly in tracking total tumor volume during treatment over time     

Neural network models in EMG diagnosis

In previous years, several computer-aided quantitative motor unit action potential (MUAP) techniques were reported. It is now possible to add to these techniques the capability of automated medical diagnosis so that all data can be processed in an integrated environment. In this study, the parametric pattern recognition (PPR) algorithm that facilitates automatic MUAP feature extraction and Artificial Neural Network (ANN) models are combined for providing an integrated system for the diagnosis of neuromuscular disorders. Two paradigms of learning for training ANN models were investigated, supervised, and unsupervised. For supervised learning, the back-propagation algorithm and for unsupervised learning, the Kohonen's self-organizing feature maps algorithm were used. The diagnostic yield for models trained with both procedures was similar and on the order of 80%. However, back propagation models required considerably more computational effort compared to the Kohonen's self-organizing feature map models. Poorer diagnostic performance was obtained when the K-means nearest neighbor clustering algorithm was applied on the same set of data     

基于特征选择的过抽样算法的研究

为了提高不平衡数据集分类中少数类的分类精度,提出了基于特征选择的过抽样算法.该算法考虑了不同的特征列对分类性能的不同作用,首先对训练集进行特征选择,选出一组特征列,然后根据选出的特征列合成少数类样本,合成的每个少数类样本的特征由两部分组成,一部分是特征选择的特征列对应的特征,另一部分是按照SMOTE原理合成的特征.将基于特征选择的过抽样算法和SMOTE算法进行实验比较,结果表明基于特征选择的过抽样算法的性能优于SMOTE算法,能有效降低数据的不平衡性,提高少数类的分类精度.